July 11, 2005.

Documentation of Power for Randomized Clinical Trials

Minn M. Soe, MD, MPH, MCTM : msoe@sph.emory.edu

Kevin M. Sullivan, PhD, MPH, MHA: cdckms@sph.emory.edu

This module estimates power for randomized clinical trials. The data input screen is as
follows:

The input values requested are:

 Two sided confidence intervals (%) that can be chosen are 25, 30, 35, 40, 45, 50, 55,
60, 65, 70, 75, 80, 85, 90, 95, 98, 99, 99.5, 99.8, 99.9, 99.95, 99.98 & 99.99.
 The available sample size for Treatment Group 1 and that for Treatment Group 2 are entered.
 The percent (proportion) of outcome in Treatment Group 1 and Treatment Group 2 are
entered ranging from 0 to 100%.

The result of the calculation is shown next:

The interpretation of power in this clinical trial is as follows: If, in truth, Treatment
Group 1 differs from Treatment Group 2 in their outcome given the above values, this
study would have 83% chance of detecting a difference without continuity correction.
The formulae for the estimation of power are as follows:

 Power with normal approximation:

( n1  2 )  z1 / 2 (1  1 /  )  p  q
Power   
( p1  q1 )  ( p2  q2 /  )

 Power with continuity correction:

(n'2 )  z1 / 2 (1  1 /  )  p  q
Power   
( p1  q1 )  ( p2  q2 /  )
Where n' = n1 - [( κ +1) / ( κ . Δ)];

 Risk ratio calculation

RR = ( p1/p2 );

The notations for the formulae are:

Δ = difference of percent of outcome between Treatment Group-1 and Treatment Group-

2;

κ = ratio of sample size: Treatment Group-2 / Treatment Group-1;

p1= percent of outcome in Treatment Group-1;

p2= percent of outcome in Treatment Group-2;

p = (p1*n1+p2*n2) / (n1+n2);

q= 1-p;

n1= sample size of Treatment Group-1;

References:
 James Schlesselman. Case-control studies: Design, Conduct, Analysis (1982).
(Formula 6.9 is used for estimation of power)
 Sahai H and KHurshid A. Formulae and tables for the determination of sample sizes
and power in clinical trials for testing differences in proportions for the two-sample
design: A review. Statistics in Medicine, 1996 vol. 15, 1-21. ((In addition to formula
6.9 mentioned above, formula 23 is used to calculate power with continuity
correction)

Acknowledgement:
Data in input screen are obtained from example 10.28 in “Bernard Rosner. Fundamentals
of Biostatistics (5th edition)”.